Overview
Kimi-K2-Instruct-0905 is a large language model from Moonshot AI, the September 2025 refresh of the Kimi K2 line.
- License: Other
- Context length: 256K tokens
- Languages: Multilingual
- Minimum hardware: ~560 GB VRAM
- Strengths: agentic coding and very long context
Highlights
- Enhanced agentic coding — significant gains on public benchmarks and real-world coding-agent tasks.
- Better frontend coding — advances in both the aesthetics and practicality of frontend work.
- 256K context — window increased from 128K to 256K for long-horizon tasks.
- 1T MoE, 32B active — trillion-parameter mixture-of-experts with modest per-token compute.
What it is good at
The model carries the code, tools, and reasoning capabilities, and its agentic and long-context tags point at where it earns its keep:
- Agentic coding — it can plan a multi-step change, call tools, and work through a task across many turns, which is the use case Moonshot AI pushed hardest in the 0905 update, including frontend work.
- Tool calling — you pass a list of available functions and the model decides when and how to invoke them, so it slots into agent loops and local automation.
- Long-context work — the 256K-token window lets it hold a large codebase, a long transcript, or several documents in one session without losing the thread.
Running it locally
This is a server-grade model. At 1026.5B total parameters even quantized builds are heavy: community GGUF quants land around 250GB+ of combined system RAM and VRAM, and higher-precision versions need far more. The 256K context also adds memory on top of the weights, so plan for a workstation with a lot of RAM rather than a single consumer GPU.
huggingface-cli download moonshotai/Kimi-K2-Instruct-0905
From there you can serve the weights through an inference engine like vLLM or SGLang, or load a quantized build through Atomic Chat to run it on-device without wiring up a server yourself.
License
Kimi-K2-Instruct-0905 ships under a custom license (listed as "other"), which Moonshot AI describes as a Modified MIT License. The weights are openly available to download and run, including local and commercial use, with the modified terms attached by the publisher — check the license text on the model's Hugging Face page before deploying at scale.